Struct SimpleCNN 

pub struct SimpleCNN { /* private fields */ }

A simple CNN for quick experiments.

Implementations

impl SimpleCNN

pub fn new(input_channels: usize, num_classes: usize) -> Self

Creates a new SimpleCNN. Note: Conv2d with kernel 3 and no padding: 28-3+1=26, after pool: 13

pub fn for_mnist() -> Self

Creates a SimpleCNN for MNIST.

pub fn for_cifar10() -> Self

Creates a SimpleCNN for CIFAR-10.

pub fn input_channels(&self) -> usize

Returns the number of input channels.

pub fn num_classes(&self) -> usize

Returns the number of classes.

Trait Implementations

impl Module for SimpleCNN

fn forward(&self, input: &Variable) -> Variable

Performs the forward pass.

fn parameters(&self) -> Vec<Parameter>

Returns all parameters of this module.

fn train(&mut self)

Sets the module to training mode.

fn eval(&mut self)

Sets the module to evaluation mode.

fn named_parameters(&self) -> HashMap<String, Parameter>

Returns named parameters of this module.

fn num_parameters(&self) -> usize

Returns the number of trainable parameters.

fn set_training(&mut self, _training: bool)

Sets the training mode.

fn is_training(&self) -> bool

Returns whether the module is in training mode.

fn zero_grad(&self)

Zeros all gradients of parameters.

fn name(&self) -> &'static str

Returns the module name for debugging.